光谱学与光谱分析 |
|
|
|
|
|
Application of Some Different Modeling Algorithms to Pear MT-Firmness Detection Using NIR Spectra |
FU Xia-ping,YING Yi-bin*,LU Hui-shan,YU Hai-yan,XU Hui-rong |
College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310029, China |
|
|
Abstract Near infrared (NIR) spectroscopy is an instrumental method, which was widely studied and used for rapid and nondestructive detection of internal qualities of agricultural products. Statistical modeling is a very important and difficult process in NIR detection to establish the relationship between nondestructive NIR spectral data and interested quality index of the products. Classical multivariate calibration methods such as partial least square regression (PLSR), principle component regression (PCR), stepwise multilinear regression (SMLR) were often used for modeling. In the present study, besides these algorithms, another mixed algorithm was adopted for establishing a nonlinear model of NIR spectra and Magness Taylor(MT) firmness of “Xueqing” pears. The mixed algorithm was combined with SMLR and artificial neural network (ANN). NIR diffuse reflectance spectra of intact pears were measured in the spectral range of 800-2 630 nm using InGaAs detector. However, only spectral information between 800 and 2 500 nm was used for modeling because of the low signal to noise ratio beyond 2 500 nm. Comparing the classical multivariate calibration methods of PLSR, PCR and SMLR, the modeling results using PLSR method were much better than the other two methods. Moreover, models based on original spectra turned out better results than models based on derivative spectra for all the three methods. The best results were r=0.87, RMSEC=3.88 N of calibration and r=0.84, and RMSEP=4.26 N of validation by using PLSR method based on original spectra. The mixed algorithm also performed better than SMLR and PCR, but was a bit worse than PLSR: r=0.85, RMSEC=4.15 N of calibration and r=0.82, and RMSEP=4.67 N of validation. The results indicated that fruit NIR spectra could be used for MT-firmness prediction when a proper algorithm was chosen, however, further study on statistic modeling is still necessary to improve the predicting performance.
|
Received: 2006-05-08
Accepted: 2006-09-23
|
|
Corresponding Authors:
YING Yi-bin
E-mail: ybying@zju.edu.cn
|
|
Cite this article: |
FU Xia-ping,YING Yi-bin,LU Hui-shan, et al. Application of Some Different Modeling Algorithms to Pear MT-Firmness Detection Using NIR Spectra[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2007, 27(05): 911-915.
|
|
|
|
URL: |
https://www.gpxygpfx.com/EN/Y2007/V27/I05/911 |
[1] McGlone V A, Kawano S. Postharvest Biology and Technology, 1998, 13: 131. [2] Fidêncio P H, Poppi R J, Andrade J C. Anal. Chim. Acta, 2002, 453: 125. [3] WANG Duo-jia, ZHOU Xiang-yang, JIN Tong-ming, et al(王多加, 周向阳, 金同铭, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2004, 24(4): 447. [4] LUO Yi-fan, GUO Zhen-fei, ZHU Zhen-yu, et al(罗一帆,郭振飞,朱振宇,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2005,25(8):1230. [5] BAI Yin-kui, MENG Xian-jiang, DING Dong, et al(白英奎,孟宪江,丁 东,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2005,25(3):381. [6] Swierenga H, Groot P J, Weijer A P, et al. Chemometrics and Intelligent Lab System, 1998, 41: 237. [7] Windig W, Stephenson D A. Anal. Chem., 1992, 64: 2735. [8] Davies A M C. NIR News, 1993, 4(4): 10. [9] Fischbacher C, Jagemann K U, Danzer K, et al. Fresenius′ J. Anal. Chem., 1997, 359: 78. [10] Carlin M, Kavli T, Lillekjendlie B. Chemometrics and Intelligent Lab System, 1994, 23: 163. [11] Cho R K, Lee K H, Iwamoto M. Spectr. Conf. R. A. Taylor, ed. West Sussex, U.K.: NIR Publications, 1992, 71. [12] Elridge C D. Int. J. Remote Sensing, 1995, 11(6): 1175. [13] Lu R. Trans. American Society Agriculture Engineers, 2001, 44(5): 1265. [14] Lu R, Ariana D. Applied Engineering in Agriculture, 2002, 18(5): 585. [15] Park B, Abbott J A, Lee K J, et al. Trans. American Society Agriculture Engineers, 2003, 46(6): 1721. [16] Ramadan Z, Hopke P K, Johnson M J, et al. Chemometrics and Intellignet Lab Systems, 2005., 75(1): 23. |
[1] |
ZHANG Fan1, WANG Wen-xiu1, ZHANG Yu-fan1, HU Ze-xuan1, ZHAO Dan-yang1, MA Qian-yun1, SHI Hai-yan2, SUN Jian-feng1*. Hyperspectral and Ensemble Learning Method for Rapid Identification of Black Spot in Yali Pear at Gley Stage[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(05): 1541-1549. |
[2] |
CHEN Jia-min1, LI Bo-yan1*, HU Yun2, ZHANG Jin1, WANG Rui-min1, SUN Xiao-hong1. Phytochemical Active Composites in Rosa Roxburghii Tratt.: Content Distribution and Spectroscopic Characterization[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(11): 3403-3408. |
[3] |
WANG Guang-lai, WANG En-feng, WANG Cong-cong, LIU Da-yang*. Early Bruise Detection of Crystal Pear Based on Hyperspectral Imaging Technology and Transfer Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(11): 3626-3630. |
[4] |
LIU Yan-de, LIAO Jun, LI Bin, JIANG Xiao-gang, ZHU Ming-wang, YAO Jin-liang, WANG Qiu. Robustness of Global Model of Soluble Solids in Gongli Pear Based on Near-Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2781-2787. |
[5] |
ZHOU Jing1,2, ZHANG Qing-qing1,2, JIANG Jin-guo2, NIE Qian2, BAI Zhong-chen1, 2*. Study on the Rapid Identification of Flavonoids in Chestnut Rose (Rosa Roxburghii Tratt) by FTIR[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(10): 3045-3050. |
[6] |
HAO Yong1, WANG Qi-ming1, ZHANG Shu-min2. Study on Online Detection Method of “Yali” Pear Black Heart Disease Based on Vis-Near Infrared Spectroscopy and AdaBoost Integrated Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(09): 2764-2769. |
[7] |
LIU Hui-jun, WEI Chao-yu, HAN Wen, YAO Yan. Determination of Huanghua Pear’s Harvest Time Based on Convolutional Neural Networks by Visible-Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(09): 2932-2936. |
[8] |
LIU Song-yang1, LIU Guang-da1, LIU Zhuo-ya2, QIU Ji-qing3*, CAI Jing1, ZHU Zhan-peng3, ZHANG Cheng3, QI Yuan3, ZHANG Shang1. Research on Extended Kalman Filter in Extracting Cerebral Blood Flow Signals by Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(07): 2048-2053. |
[9] |
CHEN Dong-jie1, 2, JIANG Pei-hong1, 2, GUO Feng-jun1, 2, ZHANG Yu-hua1, 2*, ZHANG Chang-feng1, 2. Effects of Prediction Model of Kolar Pear Based on NIR Diffuse Transmission under Different Moving Speed on Online[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(06): 1839-1845. |
[10] |
WANG Shu-tao, LIU Shi-yu*, WANG Zhi-fang, ZHANG Jing-kun, KONG De-ming, WANG Yu-tian. The Determination of Potassium Sorbate Concentration Based on ICSO-SVM Combining Three-Dimensional Fluorescence Spectra[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(05): 1614-1619. |
[11] |
SHENG Xiao-hui1, LI Zi-wen1, LI Zong-peng1, ZHANG Fu-yan2, ZHU Ting-ting3, WANG Jian1*, YIN Jian-jun1, SONG Quan-hou1. Determination of Korla Pear Hardness Based on Near-Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(09): 2818-2822. |
[12] |
NIE Li-xing, CHANG Yan, DAI Zhong, MA Shuang-cheng*. A New Method for Determination of Polysorbate 80 in Shengmai Injection Based on Absorption Coefficient[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(01): 199-203. |
[13] |
FANG Xiao-qian, PENG Yan-kun, WANG Wen-xiu, ZHENG Xiao-chun, LI Yong-yu*, BU Xiao-pu. Rapid and Simultaneous Detection of Sodium Benzoate and Potassium Sorbate in Cocktail Based on Surface-Enhanced Raman Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(09): 2794-2799. |
[14] |
HUANG Yu-ping1, Renfu Lu2, QI Chao3, CHEN Kun-jie3*. Measurement of Tomato Quality Attributes Based on Wavelength Ratio and Near-Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(08): 2362-2368. |
[15] |
YANG Yu, PENG Yan-kun, LI Yong-yu*, FANG Xiao-qian, ZHAI Chen, WANG Wen-xiu, ZHENG Xiao-chun. Calibration Transfer of Surface-Enhanced Raman Spectroscopy Quantitative Prediction Model of Potassium Sorbate in Osmanthus Wine to Other Wine[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(03): 824-829. |
|
|
|
|